lightning-architecture-review

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill's Instructions and References explicitly direct the agent to consult public third-party resources (e.g., the SuperScalar GitHub repo https://github.com/8144225309/SuperScalar and related website/forum links), which are untrusted, user-generated sources the agent would be expected to read and that could materially influence its analysis or actions.